Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c0e95c2524060bb03e967954d661150494077a2ec08936bcd1a6ca155971ff7
+oid sha256:6248ed4c653594a8de970d78de8f0e7b64bffe45fe5ee365f6b8f8b91fbd4025
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ed4ed2575dbbc818087c7af10a45b7be59ab4e0de75ff6ccfa6a30be7f6fb0
+oid sha256:b4e624766537ae45035810bd6d87e256854b78aff75a364946f39551b66fea89
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec69c1f9db00275f2bf788ed50aaee351133623fcb893d2824213ebb8d0cd795
+oid sha256:54edf57dba3a9923bec7bf6c66a78fd0774a6a561f9a15bd2287923ae584c11c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4787811040878296,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.4662799835205078,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 15.58,
       "eval_steps_per_second": 1.954,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 1.2326,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.4662799835205078,
+      "eval_runtime": 93.3055,
+      "eval_samples_per_second": 15.551,
+      "eval_steps_per_second": 1.951,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.927413222981632e+16,
+  "total_flos": 3.510926195245056e+16,
   "trial_name": null,
   "trial_params": null
 }